© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27039
    Prev
    Next
    INDEX
    Explanations

    graph vertices and nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    豫
    -0.07
    åľ¨åŃ©åŃIJ
    -0.07
    èĸĦ
    -0.07
    amba
    -0.07
    æµ·æ¶Ľ
    -0.06
     êµ´
    -0.06
    ä¸İåŃ©åŃIJ
    -0.06
    ä¸İæĻ®éĢļ
    -0.06
    æĺ§
    -0.06
    è¿ĽéĢĢ
    -0.06
    POSITIVE LOGITS
     vertices
    0.10
    vertices
    0.10
     nodes
    0.10
    Vertices
    0.10
    èĬĤçĤ¹
    0.09
     Nodes
    0.09
    nodes
    0.09
     Vert
    0.08
    vertex
    0.08
    Nodes
    0.08
    Activations Density 0.036%

    No Known Activations